Comparative Analysis of Machine Learning in Predicting the Treatment Status of COVID-19 Patients

Abstract

COVID-19 has become a global pandemic that causes many deaths, so medical treatment for COVID-19 patients gets special attention, whether hospitalized or self-isolated. However, the problem in medical action is not easy, and the most frequent mistakes are due to inaccuracies in medical decision-making. Meanwhile, machine learning can predict with high accuracy. For that, or that's why this study aims to propose a data mining classification method as a machine learning model to predict the treatment status of COVID-19 patients accurately, whether hospitalized or self-isolated. The data mining method used in this research is the Random Forest (RF) and Support Vector Machine (SVM) algorithm with Confusion Matrix and k-fold Cross Validation testing. The finding indicated that the machine learning model has an accuracy of up to 94% with the RF algorithm and up to 92% with the SVM algorithm in predicting the COVID-19 patient's treatment status. It means that the machine learning model using the RF algorithm has more accurate accuracy than the SVM algorithm in predicting or recommending the treatment status of COVID-19 patients. The implication is that RF machine learning can help/replace the role of medical experts in predicting the patient's care status.